TeamDelta/ABEJA-Qwen2.5-32B-base-jp-v0.1

Full fine-tune vs abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1. Fine-tune: 95% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 1/129, MLP 192/192, Attention 448/448, lm_head 0/1

1 derivatives checked

• mradermacher/ABEJA-Qwen2.5-32B-base-jp-v0.1-GGUF: Quantization

On the Hub · Downloads on Model Pulse